@inproceedings{wang-etal-2026-car,
title = "{CAR}: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification",
author = "Wang, Kai and
Wang, Xu and
Fu, Zhiyuan and
Zhang, Yudong and
Wang, Yang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.869/",
pages = "17551--17571",
ISBN = "979-8-89176-395-1",
abstract = "While current LLM agents utilizing paradigms like ReAct or Plan-and-Solve have established a strong foundation for step-by-step reasoning, they remain brittle in open-ended environments due to two intrinsic limitations: (1) A closed action space: These frameworks are confined to static, pre-defined toolsets, rendering them unable to adapt when required tools are missing or obsolete. (2) Myopic error recovery: Existing agents often get trapped in repetitive local retries, failing to diagnose and rectify root causes within the high-level plan. To overcome these limitations, we introduce CAR (Create And Replan), a novel architecture that incorporates a meta-tool synthesizer to dynamically augment the action space and a reflective replanning mechanism to revise global strategies. To rigorously evaluate our approach, we release ToolHop-Pro, a diagnostic benchmark with systematically pruned toolsets to simulate tool scarcity. Experiments demonstrate that CAR significantly outperforms representative baselines, validating its superior robustness where static agents fail. Code and data are available at https://github.com/Zaiz-77/car."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-car">
<titleInfo>
<title>CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>While current LLM agents utilizing paradigms like ReAct or Plan-and-Solve have established a strong foundation for step-by-step reasoning, they remain brittle in open-ended environments due to two intrinsic limitations: (1) A closed action space: These frameworks are confined to static, pre-defined toolsets, rendering them unable to adapt when required tools are missing or obsolete. (2) Myopic error recovery: Existing agents often get trapped in repetitive local retries, failing to diagnose and rectify root causes within the high-level plan. To overcome these limitations, we introduce CAR (Create And Replan), a novel architecture that incorporates a meta-tool synthesizer to dynamically augment the action space and a reflective replanning mechanism to revise global strategies. To rigorously evaluate our approach, we release ToolHop-Pro, a diagnostic benchmark with systematically pruned toolsets to simulate tool scarcity. Experiments demonstrate that CAR significantly outperforms representative baselines, validating its superior robustness where static agents fail. Code and data are available at https://github.com/Zaiz-77/car.</abstract>
<identifier type="citekey">wang-etal-2026-car</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.869/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>17551</start>
<end>17571</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification
%A Wang, Kai
%A Wang, Xu
%A Fu, Zhiyuan
%A Zhang, Yudong
%A Wang, Yang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wang-etal-2026-car
%X While current LLM agents utilizing paradigms like ReAct or Plan-and-Solve have established a strong foundation for step-by-step reasoning, they remain brittle in open-ended environments due to two intrinsic limitations: (1) A closed action space: These frameworks are confined to static, pre-defined toolsets, rendering them unable to adapt when required tools are missing or obsolete. (2) Myopic error recovery: Existing agents often get trapped in repetitive local retries, failing to diagnose and rectify root causes within the high-level plan. To overcome these limitations, we introduce CAR (Create And Replan), a novel architecture that incorporates a meta-tool synthesizer to dynamically augment the action space and a reflective replanning mechanism to revise global strategies. To rigorously evaluate our approach, we release ToolHop-Pro, a diagnostic benchmark with systematically pruned toolsets to simulate tool scarcity. Experiments demonstrate that CAR significantly outperforms representative baselines, validating its superior robustness where static agents fail. Code and data are available at https://github.com/Zaiz-77/car.
%U https://aclanthology.org/2026.findings-acl.869/
%P 17551-17571
Markdown (Informal)
[CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification](https://aclanthology.org/2026.findings-acl.869/) (Wang et al., Findings 2026)
ACL